Memory-Based vs. Context-Only Conditioning Produces Distinct Behavioral Patterns in Stateful Personalization
For researchers and developers of personalized recommender systems, this work reveals that embedding-based similarity metrics fail to capture history-grounded personalization, motivating new behavior-level diagnostics.
The study compares memory-based vs. context-only conditioning in a teacher-facing educational recommender system, finding that contextual recommendations show stronger question-level responsiveness while memory-based ones exhibit history-dependent behaviors with learner-specific differentiation. Teacher evaluations indicate both are interpretable and actionable.
We study how conditioning context shapes personalization behavior in a teacher-facing educational recommender system. We compare contextual conditioning based on the current student question with memory-based conditioning using persistent learner information. Using deviation correlation and paired statistical tests, we find that contextual recommendations exhibit stronger question-level responsiveness, while memory-based recommendations exhibit history-dependent behaviors, including learner-specific differentiation under identical input. Teacher-facing evaluation signals suggest these recommendations are interpretable and actionable. These results indicate that embedding-based similarity metrics capture responsiveness to the current question but do not characterize personalization grounded in learner history, motivating behavior-level diagnostics for studying conditioning effects.